© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7980
    Prev
    Next
    INDEX
    Explanations

    the word "bedroom" and words related to computer tasks that go wrong

    oai_token-act-pair · gemini-2.0-flash

    bedroom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    As
    -0.65
    ta
    -0.57
    fulness
    -0.56
    IONAL
    -0.55
    toPromise
    -0.53
    To
    -0.52
     As
    -0.52
    Pardon
    -0.52
    ب
    -0.50
     place
    -0.50
    POSITIVE LOGITS
    ]")]
    1.09
    IntoConstraints
    0.99
     snippetHide
    0.88
    RetentionPolicy
    0.85
     &___
    0.85
    lámpara
    0.84
    PerformLayout
    0.81
     nôtre
    0.81
    berdayakan
    0.80
     CURIAM
    0.79
    Activations Density 2.651%

    No Known Activations